ClawHub
Back to skill

Security audit

保养项目解读台

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only car maintenance advice skill with no code execution, persistence, or credential access; the main caveat is that one trigger phrase is broad.

Safe to install for automotive maintenance-list interpretation. Users should still verify safety-critical or warranty-related work against the vehicle manual or a qualified mechanic, and be aware that broad trigger wording may make the skill appear in some unrelated “should I do this” conversations.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase set includes very generic terms such as “保养项目”, “要不要做”, and “多久换机油”, which can overlap with ordinary user language outside explicit skill invocation. Overly broad triggers can cause the skill to activate unintentionally, leading to prompt hijacking of routing logic, user confusion, or the skill being selected in contexts where it was not intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.